Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1971 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.4015. Min Act: -0.0000

Data Index: 231482 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3158. Min Act: -0.0000

Data Index: 469693 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3117. Min Act: -0.0000

Data Index: 754756 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2906. Min Act: -0.0000

Data Index: 466326 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2934. Min Act: -0.0000

Data Index: 3120 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2533. Min Act: -0.0000

Data Index: 3103 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2612. Min Act: -0.0000

Data Index: 789221 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1209196 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1237808 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2509. Min Act: -0.0000

Data Index: 336657 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2633. Min Act: -0.0000

Data Index: 718200 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2445. Min Act: -0.0000

Data Index: 353733 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2302. Min Act: -0.0000

Data Index: 184308 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2393. Min Act: -0.0000

Data Index: 242216 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2454. Min Act: -0.0000

Data Index: 222266 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2243. Min Act: -0.0000

Data Index: 725527 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2205. Min Act: -0.0000

Data Index: 365223 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1456179 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2255. Min Act: -0.0000

Data Index: 183517 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2185. Min Act: -0.0000

Data Index: 366117 (C4 (Web Text))

Max Activating Token Index: 452